GIS-Based Landslide Susceptibility Mapping Using the Analytic Hierarchy Process (AHP) in Batang Kali, Selangor, Malaysia

Landslides are a prevalent environmental risk in Malaysia, occurring mainly in hilly and tropical locations, often during the optimum time for heavy downpours. This study aims to assess the landslide susceptibility in Batang Kali, Selangor, Malaysia, utilizing the Analytic Hierarchy Process (AHP) based on Geographic Information Systems (GIS). Based on historical records, aerial image interpretation, and remote sensing data, in combination with field verification, a landslide database of 46 identified landslide locations was produced. Sixteen influential factors, including various topographic, hydrological, environmental, and human factors, were selected for landslide susceptibility modeling. The landslide susceptibility map was created using weighted overlay analysis and classified into five levels of susceptibility, ranging from very low to very high. The resulting susceptibility map shows that 14.68% of the study area belongs to the very low susceptibility class, while 25.84%, 20.20%, 24.90%, and 14.38% belong to low, moderate, high, and very high susceptibility classes, respectively. The susceptibility map obtained from this study serves as a realistic decision-support tool for reducing landslide risk, designing infrastructure, and promoting sustainable land management in sensitive mountainous areas. Receiver Operating Characteristic (ROC) curve analysis was performed to measure the model's predictive performance, using the Area Under the Curve (AUC) as an overall measure of model discrimination. The ROC–AUC analysis showed an AUC value of 0.722 (72.2%), indicating acceptable model performance.